Reverse engineering of mechanical parts: A template-based approach

[Display omitted] •A novel CAD reconstruction method fitting a CAD template model to mesh data.•A feature-based parametric-associative modelling history is retrieved.•Fitting process is controlled by a Particle Swarm Optimization algorithm.•Accuracy of reconstructed models is comparable/better than state of the art results.•Computational costs and required time are at the moment considerable. Template-Based reverse engineering approaches represent a relatively poorly explored strategy in the field of CAD reconstruction from polygonal models. Inspired by recent works suggesting the possibility/opportunity of exploiting a parametric description (i.e. CAD template) of the object to be reconstructed in order to retrieve a meaningful digital representation, a novel reverse engineering approach for the reconstruction of CAD models starting from 3D mesh data is proposed. The reconstruction process is performed relying on a CAD template, whose feature tree and geometric constraints are defined according to the a priori information on the physical object. The CAD template is fitted upon the mesh data, optimizing its dimensional parameters and positioning/orientation by means of a particle swarm optimization algorithm. As a result, a parametric CAD model that perfectly fulfils the imposed geometric relations is produced and a feature tree, defining an associative modelling history, is available to the reverse engineer. The proposed implementation exploits a cooperation between a CAD software package (Siemens NX) and a numerical software environment (MATLAB). Five reconstruction tests, covering both synthetic and real-scanned mesh data, are presented and discussed in the manuscript; the results are finally compared with models generated by state of the art reverse engineering software and key aspects to be addressed in future work are hinted at.